import datetime as _dt
import html
import json
import math
import os
import re
import threading
import traceback
from collections import Counter
from pathlib import Path
from tkinter import BOTH, DISABLED, END, LEFT, NORMAL, RIGHT, StringVar, Tk, filedialog, messagebox, ttk
APP_NAME = "电脑文件夹梳理索引页生成器"
CHINESE_RE = re.compile(r"[\u4e00-\u9fff]{2,}")
WORD_RE = re.compile(r"[A-Za-z][A-Za-z0-9_\-]{2,}")
STOPWORDS = {
"the", "and", "for", "with", "from", "this", "that", "have", "has", "are", "was", "were",
"you", "your", "not", "but", "all", "can", "will", "into", "return", "class", "function",
"const", "let", "var", "true", "false", "null", "none", "import", "export", "public", "private",
"static", "void", "string", "number", "object", "array", "error", "data", "file", "path",
"一个", "没有", "以及", "进行", "可以", "需要", "使用", "通过", "如果", "因为", "所以",
"这个", "那个", "这些", "那些", "里面", "内容", "文件", "文件夹", "目录", "所有", "生成",
}
def human_size(size):
units = ["B", "KB", "MB", "GB", "TB"]
value = float(size)
for unit in units:
if value < 1024 or unit == units[-1]:
return f"{value:.1f} {unit}" if unit != "B" else f"{int(value)} B"
value /= 1024
def file_url(path):
return Path(path).absolute().as_uri()
def split_camel_and_symbols(value):
value = re.sub(r"([a-z])([A-Z])", r"\1 \2", value)
return re.sub(r"[_\-.\\/]+", " ", value)
def collect_terms(text):
counter = Counter()
text = split_camel_and_symbols(text)
for word in WORD_RE.findall(text):
word = word.lower()
if word not in STOPWORDS and not word.isdigit():
counter[word] += 1
for run in CHINESE_RE.findall(text):
if run in STOPWORDS:
continue
if len(run) <= 6:
counter[run] += 3
else:
for n in (2, 3, 4):
for i in range(0, len(run) - n + 1):
token = run[i:i + n]
if token not in STOPWORDS:
counter[token] += 1
return counter
def top_keywords(*texts, limit=12):
counter = Counter()
for text in texts:
counter.update(collect_terms(text or ""))
scored = []
for token, count in counter.items():
if len(token) < 2:
continue
bonus = 1.5 if any("\u4e00" <= ch <= "\u9fff" for ch in token) else 1.0
scored.append((count * bonus * math.log(len(token) + 1), token))
scored.sort(reverse=True)
return [token for _, token in scored[:limit]]
def scan_folder(root_path, log):
root = Path(root_path)
files = []
folder_counter = Counter()
total_size = 0
errors = []
all_keywords = Counter()
paths = []
for current, dirnames, filenames in os.walk(root):
dirnames[:] = [d for d in dirnames if d not in {".git", "node_modules", "__pycache__", ".venv", "venv"}]
for filename in filenames:
paths.append(Path(current) / filename)
total = len(paths)
log(f"发现 {total} 个文件，开始分析文件名...")
for idx, path in enumerate(paths, start=1):
try:
stat = path.stat()
rel = path.relative_to(root)
folder = str(rel.parent) if str(rel.parent) != "." else "根目录"
folder_counter[folder] += 1
total_size += stat.st_size
name_text = " ".join([path.stem, path.suffix.lower(), str(rel.parent)])
keywords = top_keywords(name_text)
all_keywords.update(keywords)
files.append({
"name": path.name,
"relativePath": str(rel).replace("\\", "/"),
"folder": folder.replace("\\", "/"),
"absolutePath": str(path),
"fileUrl": file_url(path),
"folderUrl": file_url(path.parent),
"extension": path.suffix.lower() or "(无扩展名)",
"size": stat.st_size,
"sizeText": human_size(stat.st_size),
"modified": _dt.datetime.fromtimestamp(stat.st_mtime).strftime("%Y-%m-%d %H:%M"),
"keywords": keywords,
"searchText": " ".join([path.name, str(rel), " ".join(keywords)]).lower(),
})
except Exception:
errors.append(f"{path}: {traceback.format_exc(limit=1).strip()}")
if idx % 100 == 0 or idx == total:
log(f"已分析 {idx}/{total} 个文件")
files.sort(key=lambda item: item["relativePath"].lower())
return {
"root": str(root),
"generatedAt": _dt.datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
"fileCount": len(files),
"folderCount": len(folder_counter),
"totalSize": total_size,
"totalSizeText": human_size(total_size),
"topKeywords": [k for k, _ in all_keywords.most_common(30)],
"topFolders": folder_counter.most_common(30),
"errors": errors[:80],
"files": files,
}
HTML_TEMPLATE = r"""
文件夹索引 - __TITLE__
"""
def write_html_index(data, output_path):
payload = json.dumps(data, ensure_ascii=False)
title = html.escape(Path(data["root"]).name or "root")
content = HTML_TEMPLATE.replace("__TITLE__", title).replace("__DATA__", payload.replace("